Prediction of abrasive wears behavior of dental composites using an artificial neural network

Abstract

Resin composites are widely used as dental restorative materials since dental parts are subjected to prolonged wear and ultimately need to be replaced. The objective of this study is to analyze the potential of the feed-forward back propagation artificial neural network (ANN) in assessing the wear of dental composite materials when immersed in chewable tobacco solution, by utilizing the in-vitro test results of the pin-on-disc tribometer [ASTM G99-04]. In this study, four different dental composite material specimens are dipped in a chewable tobacco solution for a few days, and the specimens are removed from the solution for conducting the wear test. Three different training procedures are used to simulate ANN models for predicting the wear of dental composite specimens. The Bayesian regularization training algorithm outperforms the other algorithms significantly. The findings of the ANN modeling were prominently matching with the results of the experiments; therefore, parametric analysis was used based on the model's predicted values.